GitHub

mcp

Run the local MCP server so agents can drive squirrelscan

The mcp command starts a local Model Context Protocol server over stdio. Agents like Claude Code and Cursor launch it to call squirrelscan’s audit engine and cloud features as tools.

Usage

bash
squirrel mcp

The server runs in the foreground and speaks JSON-RPC on stdin/stdout. You rarely run it directly. Your agent spawns it from its MCP config. See the MCP Server guide for connect instructions.

Tools

ToolAuthDescription
audit_websiteNoneFull deterministic audit of a URL; cloud enrichment added when logged in.
quick_checkNoneFast, local-only single-pass health check of one URL.
list_rulesNoneList all built-in audit rules.
get_ruleNoneFull definition of one rule by id.
list_auditsLoginYour org’s running/pending audits.
get_reportLoginFetch a published report by audit id.
list_issuesLoginSupplant-aware issue state for a website.
get_issueLoginA single issue by website + number.
comment_on_issueLoginComment on an audit issue.

Authentication for agent/CI use

Tools marked “Login” above need a credential to reach the squirrelscan API. The local server reuses the same token resolution as the rest of the CLI: it checks SQUIRRELSCAN_API_KEY (or the older SQUIRREL_API_TOKEN alias) first, then falls back to a squirrel auth login session.

For a headless agent or CI runner that spawns squirrel mcp without ever calling squirrel auth login, set the env var on the process:

bash
SQUIRRELSCAN_API_KEY=sq_xxxxxxxxxxxx squirrel mcp

If neither the env var nor a login session is present, an authed tool call returns a clear error naming both fixes instead of a generic failure. A call that’s denied for lacking a scope (e.g. an audits:read-only key calling a write tool) names the missing scope in the error text as well.

Quick start with Claude Code

bash
claude mcp add squirrelscan -- squirrel mcp

Type to search…

↑↓ navigate open esc close